GAFSV-Net: A Vision Framework for Online Signature Verification

GAFSV-Net：用于在线签名验证的视觉框架

Abstract: Online signature verification (OSV) requires distinguishing skilled forgeries from genuine samples under high intra-class variability and with very few enrollment samples. Existing deep learning methods operate directly on raw temporal sequences, restricting them to 1D architectures and preventing the use of pretrained 2D vision backbones.

摘要： 在线签名验证（OSV）需要在高类内变异性且注册样本极少的情况下，将高水平的伪造签名与真实样本区分开来。现有的深度学习方法直接对原始时间序列进行操作，这限制了它们只能使用一维架构，从而无法利用预训练的二维视觉骨干网络。

We bridge this gap with GAFSV-Net, which represents each signature as a six-channel asymmetric Gramian Angular Field image: three kinematic channels (pen speed, pressure derivative, direction angle) are each encoded into complementary GASF and GADF matrices that capture pairwise temporal co-occurrence and directional transition structure respectively.

我们通过 GAFSV-Net 弥补了这一差距。该框架将每个签名表示为六通道非对称格拉姆角场（Gramian Angular Field）图像：三个运动学通道（笔速、压力导数、方向角）分别被编码为互补的 GASF 和 GADF 矩阵，分别捕捉成对的时间共现结构和方向转换结构。

A dual-branch ConvNeXt-Tiny encoder processes GASF and GADF independently, with bidirectional cross-attention enabling each branch to query discriminative patterns from the other before metric-space projection. Training uses semi-hard triplet loss with skilled-forgery hard-negative injection; verification is performed via cosine similarity against a small enrollment prototype.

双分支 ConvNeXt-Tiny 编码器独立处理 GASF 和 GADF，并通过双向交叉注意力机制，使每个分支在投影到度量空间之前，能够从另一个分支查询判别性模式。训练过程采用了带有高水平伪造硬负样本注入的半硬三元组损失（semi-hard triplet loss）；验证则通过计算与少量注册原型之间的余弦相似度来完成。

We evaluate on DeepSignDB and BiosecurID, outperforming all sequence-based baselines trained under identical objectives, demonstrating that the representational gain of 2D temporal encoding is consistent and independent of training procedure, with ablations characterising each design choice’s contribution.

我们在 DeepSignDB 和 BiosecurID 数据集上进行了评估，结果优于所有在相同目标下训练的基于序列的基准模型。这证明了二维时间编码带来的表征增益是稳健的，且独立于训练过程；同时，消融实验也明确了每一项设计选择的具体贡献。